Blog

Customer Spotlight: Rio Tinto

Posted by Jess Lin

19.12.2013 10:34 AM

We have amazing customers doing even more amazing things with their data. As we hear from our customers with their stories, we will be sharing them with you here on our blog. Hopefully they will help inspire you to think about what more you could be doing with your own data! Contact us if you have a case study using Eureqa you would like to share as well.

Rio Tinto

As a major supplier of iron and steel powder to North American, Europe, and Asia auto parts industries, Rio Tinto, Fer et Titane (RTFT), carefully watches specifications for the products it manufactures to ensure consistent product quality. RTFT has seen a large increase in demand for steel powder recently, as many manufacturers have been switching to an efficient powder-based manufacturing approach. However, changing specifications in one of their iron powders was resulting in some batches not passing Rio Tinto’s high standards for quality.

Marko Litalien, Superintendent of Process Development for RTFT’s Steel and Powder Division, decided to try out Eureqa after seeing its past success in deriving laws of physics. After only 45 minutes of searching through the mountains of data Litalien provided, Eureqa was able to find a variable that was linked to the slipping specification, one that none of the engineers had previously considered. The R&D engineers had to spend several days confirming the variable’s effect on the specification, but the team saw success immediately after putting controls on the variable into effect. The process engineer overseeing the change commented, “We’re living in an era where we have an enormous amount data that no one really understands. When I see software like this that can take that data and make sense of it, I think we’re going in the right direction.”

For more details, read the full case study here!

Topics: Case study, Eureqa

Customer Spotlight: Radnostics

Posted by Jess Lin

19.11.2013 10:00 AM

We have amazing customers doing even more amazing things with their data. As we hear from our customers with their stories, we will be sharing them with you here on our blog. Hopefully they will help inspire you to think about what more you could be doing with your own data! Contact us if you have a case study using Eureqa you would like to share as well.

The diagnosis of acute appendicitis requires immediate surgery in cases where the appendix is still intact. To avoid exposing children to ionizing radiation in CT scans, ultrasound can be used to detect other features of the appendix and the surrounding area, but is unable to directly reveal the presence or absence of a perforation in the appendix. A team led by Dr. Einat Blumfield worked to discover the specific, associated ultrasound findings that would accurately point to perforation. Given the ultrasound images of 161 subjects diagnosed with acute appendicitis, the researchers needed to find a model that would identify correlations in the data.

Anthony Blumfield, the statistical modeler for the team, got a suggestion from his former classmate Hod Lipson (now advisor to Nutonian), to download Eureqa and use the power of symbolic regression to find a model for the data. After setting the software to work, Anthony Blumfield returned a couple hours later to find that the software had already found a model that predicted perforation as accurately as CT scans. More surprisingly, the model had discovered age categories that better defined which ultrasound findings would predict perforation. “We want to look at clinical findings that are associated with perforation such as duration of symptoms, white blood count, and fever,” Dr. Einat Blumfield explains. “We’ll then use Eureqa to search for a formula that combines ultrasound findings and clinical findings, and we hope to achieve an even higher level of accuracy.”

For more details, read the full case study here!

Jess

Topics: Case study, Eureqa, hod lipson, Modeling Outputs

Customer Spotlight: Cypress Point Technologies

Posted by Jess Lin

12.11.2013 10:00 AM

We have amazing customers doing even more amazing things with their data. As we hear from our customers with their stories, we will be sharing them with you here on our blog. Hopefully they will help inspire you to think about what more you could be doing with your own data! Contact us if you have a case study using Eureqa you would like to share as well.

Trin iconCypress Point Technologies creates tools that allow hedge fund managers to analyze the New York and NASDAQ stock exchanges. Charles Brauer founded Cypress Point Technologies in 2009 after seeing success with his side project, HedgeTools. Two years later, Brauer and his team began to work on expanding HedgeTool’s capabilities with custom models that use early-morning stock data to predict stock price trajectories through the rest of the day. Given the complexity of the task and the number of trends that could turn out to be false positives, it was crucial for the team to develop a sophisticated yet lightning-fast algorithm that was capable of producing accurate predictions.

After seeing a story in Wired Magazine about Eureqa, Brauer decided to download the software and get in contact with Nutonian founder and CEO Michael Schmidt. In his first few trial runs with Eureqa, Brauer took historical, minute-by-minute price data for a batch of stocks, pre-categorize them as “good” or “bad”, and let Eureqa come up with an algorithm that could predict trajectories based on the first 30 minutes of market activity. The results were impressive enough on the initial, minimal dataset, but after adding in additional parameters and refinements, the resulting models have been making increasingly accurate predictions. Most importantly for Brauer, the speed and accuracy of generating and applying models makes them easy to deploy within HedgeTools. “I have a test portfolio that’s managed based on recommendations from HedgeTools,” says Brauer, “and it beats the performance of the S&P 500 by a wide margin.”

For more details, read the full case study here!

Topics: Case study, Cypress Point, Eureqa, Making predictions

Customer Spotlight: Performance Genetics

Posted by Jess Lin

05.11.2013 10:00 AM

We have amazing customers doing even more amazing things with their data. As we hear from our customers with their stories, we will be sharing them with you here on our blog. Hopefully they will help inspire you to think about what more you could be doing with your own data! Contact us if you have a case study using Eureqa you would like to share as well.

describe the imagePerformance Genetics empowers their customers to make confident purchasing decisions at yearling and two-year-old training sales. Using a combination of practical horse knowledge and horsemanship along with an intensely computational approach to data, they are able to spot elite potential in not-yet-raced horses. Knowing the key data points for generating an accurate prediction and being able to gather and analyze those data points quickly is critical in giving Performance Genetics an edge in the sale ring.

CEO Byron Rogers tried out Eureqa after his partner, Alan Porter, saw the software featured in a New Scientist article. Using Eureqa to analyze a historical data set, Rogers quickly determined that the tool returned powerful models that were immediately applicable in the field. Eureqa’s models were able to simplify the prediction algorithm with no loss to accuracy, generating improved algorithms with fewer data points. This had the added benefit of not only allowing Rogers to generate predictions on the field more quickly, but also freeing him to focus on capturing more nuances in the remaining, key data points. “As with the biomechanical data, I expect that Eureqa’s ability to pick out the important data points in these other areas, along with its ability to make use of prior solutions, will be integral in the development of a unified model,” he says. “It’s going to be very interesting.”

For more details, read the full case study here!

Topics: Case study, Eureqa, Modeling Outputs

Follow Me

Posts by Topic

see all